# Gemini 3 Pro vs GPT-6 Sol

> Gemini 3 Pro is the stronger model overall, scoring 54.7 to 49.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-pro-vs-gpt-6-sol
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemini 3 Pro scores higher in 8 categories and GPT-6 Sol in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3 Pro leads 64.3 to 43.0.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 13.6% for Gemini 3 Pro and 6.5% for GPT-6 Sol.

## Snapshot

| | Gemini 3 Pro | GPT-6 Sol |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 54.7 | 49.2 |
| Rank | 23 | 46 |
| Context | — | 1.05M |
| Input $/M | — | $2 |
| Output $/M | — | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3 Pro: 52.1 (#33)
- GPT-6 Sol: 59.6 (#11)

| Benchmark | Gemini 3 Pro | GPT-6 Sol |
|---|---|---|
| LMArena WebDev | 1439 | 1692 |
| LMArena Coding | 1482 | 1453 |
| SWE-bench Verified | 72.9% | — |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| SWE-bench Verified (bash only) | 74.2% | — |
| SWE-bench Multilingual | 68.7% | — |
| GSO | 18.6% | — |
| WeirdML | 69.9% | — |
| ALE-Bench | 1,177 | — |
| AlgoTune | 1.83 | — |

## Agentic & Tool Use

- Gemini 3 Pro: 40.5 (#21)
- GPT-6 Sol: 33.5 (#49)

| Benchmark | Gemini 3 Pro | GPT-6 Sol |
|---|---|---|
| Terminal-Bench | 69.4% | — |
| Berkeley Function Calling Leaderboard | 72.5% | — |
| GDPval | 40.3% | — |
| Remote Labor Index | 1.3% | — |
| τ²-bench Airline | 80.5% | — |
| τ²-bench Banking | 18% | — |
| τ²-bench Retail | 75.9% | — |
| τ²-bench Telecom | 91% | — |
| DeepResearch Bench | 46.3% | — |
| BALROG | 58.1% | — |
| GDP.pdf | — | 28% |
| LMArena Search | 1207 | — |
| METR Time Horizons | 71% | — |
| Vending-Bench 2 | 5,478 | — |

## Reasoning

- Gemini 3 Pro: 52.5 (#28)
- GPT-6 Sol: 49.3 (#34)

| Benchmark | Gemini 3 Pro | GPT-6 Sol |
|---|---|---|
| NYT Connections (extended) | 94.4% | 90.1% |
| LMArena Hard Prompts | 1481 | 1420 |
| ARC-AGI-2 | 31.1% | — |
| SimpleBench | 76.4% | — |
| Kagi LLM Benchmark | 80.1% | — |
| ARC-AGI-1 | 75% | — |
| CritPt | 6.9% | — |
| Chess Puzzles | 31% | — |
| EnigmaEval | 18.2% | — |
| EBR-Bench | — | 53.3% |
| Epoch Capabilities Index | 152.96 | — |
| ForecastBench | 61.2 | — |

## Math

- Gemini 3 Pro: 48.8 (#50)
- GPT-6 Sol: 35.8 (#135)

| Benchmark | Gemini 3 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Math | 1475 | 1404 |
| MathArena Final-Answer Competitions | 67% | — |
| OTIS Mock AIME 2024-2025 | 91.4% | — |
| ProofBench | 20% | — |
| Omni-MATH | 55.5% | — |
| FrontierMath (Feb 2025 set) | 37.6% | — |
| FrontierMath Tier 4 (v1) | 18.8% | — |

## Knowledge

- Gemini 3 Pro: 64.3 (#15)
- GPT-6 Sol: 43.0 (#87)

| Benchmark | Gemini 3 Pro | GPT-6 Sol |
|---|---|---|
| Vectara Hallucination Rate | 13.6% | 6.5% |
| LMArena Expert | 1475 | 1449 |
| GPQA Diamond | 92.6% | — |
| Humanity's Last Exam | 37.5% | — |
| MMLU-Pro | 90.3% | — |
| GPQA (HELM) | 80.3% | — |

## Multimodal

- Gemini 3 Pro: 56.9 (#1)
- GPT-6 Sol: 47.6 (#9)

| Benchmark | Gemini 3 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1305 | — |
| GeoBench | 84% | — |
| VPCT | 91% | — |
| Furniture Assembly | — | 58.3% |
| LMArena Document | 1434 | — |

## Multilingual

- Gemini 3 Pro: 57.1 (#14)
- GPT-6 Sol: 51.0 (#113)

| Benchmark | Gemini 3 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1474 | 1389 |
| LMArena Chinese | 1522 | 1416 |
| LMArena Russian | 1493 | 1407 |
| LMArena Spanish | 1468 | 1377 |
| LMArena French | 1492 | — |
| LMArena German | 1517 | — |
| LMArena Japanese | 1513 | — |
| LMArena Korean | 1449 | — |

## Instruction Following

- Gemini 3 Pro: 76.4 (#42)
- GPT-6 Sol: 74.4 (#97)

| Benchmark | Gemini 3 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1458 | 1406 |
| IFEval | 87.7% | — |

## Long Context

- Gemini 3 Pro: 44.0 (#75)
- GPT-6 Sol: 43.2 (#100)

| Benchmark | Gemini 3 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1472 | 1415 |
| CL-bench | 15.8% | — |

## Writing & Preference

- Gemini 3 Pro: 66.6 (#34)
- GPT-6 Sol: 72.3 (#15)

| Benchmark | Gemini 3 Pro | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1479 | 1396 |
| LMArena Creative Writing | 1482 | 1392 |
| EQ-Bench Creative Writing | 1525 | 2125 |
| LMArena Multi-Turn | 1484 | 1405 |
| WildBench | 85.9% | — |

## FAQ

### Is Gemini 3 Pro better than GPT-6 Sol?

Gemini 3 Pro is the stronger model overall, scoring 54.7 to 49.2 on the Noometry Index.

### Is Gemini 3 Pro or GPT-6 Sol better for coding?

GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 52.1 in the Noometry coding category.

### How many benchmarks do Gemini 3 Pro and GPT-6 Sol share?

17 benchmarks have published results for both models. Gemini 3 Pro has 67 scored results on Noometry and GPT-6 Sol has 22.